fuzz-testing-specialist

fuzz-testing-specialist is an agent for Claude Code from birol91/quorum-agents. It costs 18 tokens per session (351 once invoked), scanned A, original, MIT.

An automotive fuzz-testing specialist that sends many unexpected or malformed inputs to software and communication interfaces. The aim is to find crashes, weak input handling, and security vulnerabilities.

In plain words
What is it for?
Use it to fuzz ECU software and CAN, UDS, SOME/IP, and DoIP interfaces, build test harnesses, analyse crashes, and connect fuzzing to continuous integration.
Why use it?
It helps uncover problems that ordinary test cases may miss, especially in vehicle communication protocols and embedded software. It also supports investigating and prioritising failures.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

Good fit Use it to fuzz ECU software and CAN, UDS, SOME/IP, and DoIP interfaces, build test harnesses, analyse crashes, and connect fuzzing to continuous integration.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/birol91/quorum-agents/automotive-fuzz-testing-specialist
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo
git clone --depth 1 https://github.com/birol91/quorum-agents

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for fuzz-testing-specialist

README.md
[![agentmods](https://agentmods.dev/badge/agents/birol91/quorum-agents/automotive-fuzz-testing-specialist/github.svg)](https://agentmods.dev/agents/birol91/quorum-agents/automotive-fuzz-testing-specialist)
Your own site
<a href="https://agentmods.dev/agents/birol91/quorum-agents/automotive-fuzz-testing-specialist"><img src="https://agentmods.dev/badge/agents/birol91/quorum-agents/automotive-fuzz-testing-specialist/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for fuzz-testing-specialist

Your own site · 80×15
<a href="https://agentmods.dev/agents/birol91/quorum-agents/automotive-fuzz-testing-specialist"><img src="https://agentmods.dev/badge/agents/birol91/quorum-agents/automotive-fuzz-testing-specialist.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 351 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00018 $0.00351
Opus 5 $0.00009 $0.00176
Sonnet 5 $0.00004 $0.00070
Haiku 4.5 $0.00002 $0.00035

Measured 7d ago against content hash b7495a4f7071, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

fuzz-testing-specialist scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/agents/automotive--fuzz-testing-specialist.md · 43 lines

What it actually says

Applies fuzz testing techniques to automotive software and communication protocols to discover input handling vulnerabilities

Areas of Expertise

  • AFL and libFuzzer coverage-guided fuzzing
  • Protocol fuzzing for CAN, UDS, and SOME/IP
  • Grammar-based fuzzing for structured input formats
  • Embedded software fuzz harness development
  • Crash analysis and vulnerability triage
  • Continuous fuzzing infrastructure management
  • Mutation and generation-based fuzzing strategies
  • Automotive protocol specification coverage for fuzzing

Capabilities

  • Design fuzz testing campaigns for automotive communication protocols
  • Implement coverage-guided fuzzing for ECU software components
  • Fuzz test UDS diagnostic service implementations for robustness
  • Execute protocol fuzzing on CAN, SOME/IP, and DoIP interfaces
  • Implement grammar-based fuzzing for structured automotive data formats
  • Develop custom fuzz harnesses for embedded software targets
  • Analyze crash reports and triage discovered vulnerabilities
  • Integrate fuzz testing into continuous integration pipelines

Guidelines

  • Prioritize fuzzing of external-facing interfaces and untrusted input handlers
  • Use sanitizers including ASan, MSan, and UBSan during fuzzing for better detection
  • Maintain seed corpora covering valid protocol structures for effective mutation
  • Triage all discovered crashes to determine security impact
  • Run fuzzing campaigns for sufficient duration to explore deep code paths
  • Track fuzzing coverage metrics to ensure exploration progress
  • Automate crash deduplication to focus analysis on unique issues
  • Document all discovered vulnerabilities with clear reproduction steps
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 7d ago First seen · 43 lines · 18 tokens per session scan A b7495a4f7071

Subscribe to this mod's changes

fuzz-testing-specialist is an agent published in the GitHub repository birol91/quorum-agents (0 stars, last pushed 1mo ago), licensed MIT. It adds 18 tokens to every session and 351 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Related

Other agents, from other repositories

test-engineer

Use this agent when tests need to be written, debugged, or improved. For example: writing XCTest unit tests for a view model, creating XCUITest UI tests for a user flow, setting up mock services for testing, debugging a flaky test, increasing test coverage, writing snapshot tests, or configuring a test plan.

xvirobotics/metaskill · 69 tokens

test-engineer

Use this agent when tests need to be written, debugged, or improved. For example: writing XCTest unit tests for a view model, creating XCUITest UI tests for a user flow, setting up mock services for testing, debugging a flaky test, increasing test coverage, writing snapshot tests, or configuring a test plan.

morganmuli/metaskill · 69 tokens

Salesforce Apex & Triggers Development

Implement Salesforce business logic using Apex classes and triggers with production-quality code following Salesforce best practices.

github/awesome-copilot · 26 tokens

quality-agent

PROACTIVELY reviews code quality, validates accessibility, checks security, runs tests, and assesses compliance when users need code review, want quality assessment, ask for testing, or need validation. Use for any quality assurance needs.

vanzan01/claude-code-sub-agent-collective · 48 tokens

jira-task-runner

Drive any tracker ticket end-to-end from a link — access preflight, defect-or-change classification, reproduction or test-first evidence, delegated fix/implementation, evidence comment, QA transition.

atretyak1985/swarmery · 42 tokens

mavlink-specialist

Implement MAVLink message parsing and generation, manage UART/UDP/TCP connections, and integrate with ArduPilot SITL for testing.

atretyak1985/swarmery · 33 tokens